Sijia Li will be speaking on "Data fusion under mixed censoring types" this Wednesday, January 14th at 3:30pm in HSSB 1173
Title: Data fusion under mixed censoring types
Abstract:
In this talk, we introduce a semiparametric data fusion framework for estimating survival probabilities by integrating right-censored and current status data. Existing data fusion methods focus largely on fusing right-censored data only, while standard meta-analysis approaches are inadequate as estimators based on current status data alone typically converge at slower rates and have non-normal limiting distributions. In this work, we consider a semiparametric model under exchangeable event time distribution across data sources, and derive the canonical gradient of the survival probability at a given time. We propose an efficient estimator that attains the semiparametric efficiency bound under mild conditions. Importantly, we show that incorporating current status data can lead to meaningful efficiency gains despite the slower convergence rate of current status–only estimators. We evaluate the performance of the proposed method through simulations and illustrate its application in estimating the time to dementia onset.